© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160502
    Prev
    Next
    INDEX
    Explanations

    romantic attraction

    np_acts-logits-general · gemini-2.5-flash-lite

    romance and flirting hints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समझौ
    0.52
    贖
    0.50
     రక్త
    0.46
    🖕
    0.46
    妊娠
    0.46
    毒
    0.45
     समझौते
    0.44
    癫
    0.44
    罪
    0.43
     سزا
    0.43
    POSITIVE LOGITS
     flirt
    0.78
     romance
    0.74
     romant
    0.73
     flirting
    0.69
     romances
    0.67
     courtship
    0.66
     Romance
    0.65
     courting
    0.63
    戀
    0.63
     attraction
    0.59
    Activations Density 0.086%

    No Known Activations